Pixel Weighted Average Strategy for Depth Sensor Data FusionShow others and affiliations
2010 (English)In: 2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, Institute of Electrical and Electronics Engineers (IEEE) , 2010, p. 2805-2808Conference paper, Published paper (Refereed)
Abstract [en]
This paper introduces a new multi-lateral filter to fuse low-resolution depth maps with high-resolution images. The goal is to enhance the resolution of Time-of-Flight sensors and, at the same time, reduce the noise level in depth measurements. Our approach is based on the joint bilateral upsampling, extended by a new factor that considers the low reliability of depth measurements along the low-resolution depth map edges. Our experimental results show better performances than alternative depth enhancing data fusion techniques.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2010. p. 2805-2808
Series
IEEE International Conference on Image Processing (ICIP), ISSN 1522-4880
Keywords [en]
Machine vision, active vision, multisensor systems, image resolution, nonlinear filters.
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:kth:diva-63170DOI: 10.1109/ICIP.2010.5651112ISI: 000287728002220Scopus ID: 2-s2.0-78651112669ISBN: 978-1-4244-7994-8 (print)OAI: oai:DiVA.org:kth-63170DiVA, id: diva2:481737
Conference
IEEE International Conference on Image Processing, Hong Kong, PEOPLES R CHINA, SEP 26-29, 2010
Note
QC 20120123
2012-01-222012-01-222022-06-24Bibliographically approved